[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83573-en":3,"doc-seo-83573-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83573,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation","Scientific publication growth makes tracking and synthesizing research progress increasingly difficult. While LLMs can generate automated survey papers, existing approaches rely on unstructured retrieval and force models to infer conceptual, methodological, and taxonomic relationships during generation. STRUCTSURVEY introduces a hierarchical multiagent framework that moves structural reasoning into retrieval via dynamic, graph-based entity and relation extraction. Experiments on a new ACL reference-grounded benchmark show higher ROUGE recall and better logical structure ratings, aligning survey organization more closely with human writing.","STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation  \nPaolo Pedinotti*  \nBloomberg [pedinotti.paolo@gmail.com](pedinotti.paolo@gmail.com)  \nEnrico Santus  \nBloomberg [esantus@bloomberg.net](esantus@bloomberg.net)  \narXiv :2607 .01243v1 [ cs .IR] 12 May 2026  \nAbstract  \nThe rapid growth of scientific publications makes it increasingly difficult to track and synthesize research progress. While Large Language Models (LLMs) can support automated survey generation, existing methods retrieve unstructured data and require models to infer conceptual, methodological, and taxonomic relations from raw text at generation time. We introduce STRUCTSURVEY, a hierarchical multiagent framework that shifts structural reasoning from generation to retrieval by dynamically constructing graph-based representations of entities, relations, and topical taxonomies. We evaluate STRUCTSURVEY on a new referencegrounded benchmark of ACL survey papers for reproducible long-form scientific summarization. Compared with embedding-only retrieval baselines, STRUCTSURVEY improves ROUGE- 1 recall by +2.9 and ROUGE-2 recall by +1.0 on average, without reducing precision. It also improves LLM-as-a-Judge ratings for logical structure, depth, and synthesis, showing that explicit structural retrieval yields surveys closer to human-written organization and reasoning.  \n1 Introduction  \nThe rapid growth of scientific publications has made it increasingly difficult for researchers to identify, interpret, and synthesize relevant developments. Scientific surveys address this challenge by organizing fragmented contributions into coherent narratives that reveal conceptual structure, methodological evolution, and emerging trends. However, writing high-quality surveys remains labor-intensive, requiring domain expertise, careful source selection, and substantial time.  \nThis has motivated work on automated survey paper generation (Wang et al., 2024 ; Yan et al., 2025), where Large Language Models (LLMs) assist in retrieving, organizing, and synthesizing re-  \n*Paolo Pedinotti contributed to this work during his internship at Bloomberg.  \nsearch literature. Survey generation is particularly demanding because it requires not only factual grounding, but also the ability to identify relationships among methods, tasks, datasets, and research directions across many papers.  \nExisting systems typically rely on RetrievalAugmented Generation (RAG) (Lewis et al., 2020), retrieving semantically relevant documents and passing them to the LLM as evidence. While this improves grounding, current approaches use unstructured retrieval: retrieved passages provide no explicit representation of how ideas relate, how entities cluster, or how methods connect across the literature. This is a key limitation for survey writing, where quality depends not only on retrieving relevant papers but also on organizing them into coherent conceptual and methodological groupings. As a result, LLMs must reconstruct the conceptual scaffolding of a survey implicitly during generation, which is especially difficult for hierarchical documents organized into sections, subsections, and fine-grained themes.  \nWe introduce STRUCTSURVEY, a hierarchical multi-agent framework that incorporates structured retrieval (Jiang et al., 2025) into survey generation. Instead of relying only on vector search, STRUCTSURVEY uses parameterized query functions that trigger on-demand extraction of entities, relations, and taxonomic groupings from retrieved abstracts. These outputs are merged into an evolving domain graph that captures relationships among methods, tasks, and research directions as the outline expands. Figure 1 illustrates this process. By shifting structural reasoning from generation to retrieval, STRUCTSURVEY provides explicit, interpretable context for outline formation and narrative synthesis.  \nTo evaluate this approach, we construct a new ACL Survey Dataset of 33 survey papers published bet","cbCaigfyJvHLx9U8","https://ap.wps.com/l/cbCaigfyJvHLx9U8","pdf",656657,3,1,20,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"What problem does STRUCTSURVEY address in automated survey paper generation?\",\"answer\":\"It targets the difficulty of synthesizing fast-growing scientific literature and the limitation of unstructured retrieval that leaves LLMs to reconstruct relationships implicitly during generation.\"},{\"question\":\"How does STRUCTSURVEY differ from embedding-only or standard RAG approaches?\",\"answer\":\"Instead of vector-only retrieval, it uses parameterized query functions to extract entities, relations, and taxonomic groupings from retrieved abstracts, then merges them into an evolving domain graph to guide outlining and synthesis.\"},{\"question\":\"What evaluation evidence is reported for STRUCTSURVEY?\",\"answer\":\"On a new ACL reference-grounded benchmark of 33 survey papers (2018–2025), it improves ROUGE-1 and ROUGE-2 recall over embedding-only baselines without reducing precision, and it improves LLM-as-a-Judge ratings for logical structure, depth, and synthesis.\"}]",1784188933,50,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"structsurvey-structured-agentic-retrieval-for-automated-survey-paper-generation","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/structsurvey-structured-agentic-retrieval-for-automated-survey-paper-generation/83573/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does STRUCTSURVEY address in automated survey paper generation?","Question",{"text":75,"@type":76},"It targets the difficulty of synthesizing fast-growing scientific literature and the limitation of unstructured retrieval that leaves LLMs to reconstruct relationships implicitly during generation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does STRUCTSURVEY differ from embedding-only or standard RAG approaches?",{"text":80,"@type":76},"Instead of vector-only retrieval, it uses parameterized query functions to extract entities, relations, and taxonomic groupings from retrieved abstracts, then merges them into an evolving domain graph to guide outlining and synthesis.",{"name":82,"@type":73,"acceptedAnswer":83},"What evaluation evidence is reported for STRUCTSURVEY?",{"text":84,"@type":76},"On a new ACL reference-grounded benchmark of 33 survey papers (2018–2025), it improves ROUGE-1 and ROUGE-2 recall over embedding-only baselines without reducing precision, and it improves LLM-as-a-Judge ratings for logical structure, depth, and synthesis.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,126,129,133],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":29,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":22,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":22,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]